LLM EXPLORER 61,755 MODELS INDEXED

Swift Qwen3.8 27B Heretic by akumaburn

By akumaburn · 64 downloads
HF Repo ↗ Copy URL

Swift Qwen3.8 27B Heretic is an open-source language model by akumaburn. Features: 27b LLM, VRAM: 54.7GB, License: other, LLM Explorer Score: 0.29.

  Abliterated Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.8-27b   Conversational   Heretic   Image-text-to-text   Mtp   Qwen3.8   Qwen3 5   Region:us   Research-only   Safetensors   Sharded   Swift   Tensorflow   Uncensored   Vision
Model Card on HF 🤗: https://huggingface.co/akumaburn/Swift-Qwen3.8-27b-heretic 

Swift Qwen3.8 27B Heretic Parameters and Internals

LLM NameSwift Qwen3.8 27B Heretic
Repository 🤗https://huggingface.co/akumaburn/Swift-Qwen3.8-27b-heretic 
Base Model(s)  UkisAI/Swift-Qwen3.8-27b   Qwen/Qwen3.8-27B   UkisAI/Swift-Qwen3.8-27b   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM54.7 GB
Updated2026-09-20
Maintainerakumaburn
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-12   4.8 GB: 2-of-12   5.0 GB: 3-of-12   4.9 GB: 4-of-12   5.0 GB: 5-of-12   4.9 GB: 6-of-12   4.9 GB: 7-of-12   5.0 GB: 8-of-12   5.0 GB: 9-of-12   4.9 GB: 10-of-12   5.0 GB: 11-of-12   2.8 GB: 12-of-12   0.8 GB
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.6.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Swift Qwen3.8 27B Heretic

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB1461
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.6 27B FP80K / 0.4 GB7740472342
Qwen3.5 27B0K / 55.2 GB25362941028
Note: green Score (e.g. "73.2") means that the model is better than akumaburn/Swift-Qwen3.8-27b-heretic.